VERDICT verifies each reasoning step of a multimodal LLM by combining scores from three frozen judges through a closed-form consensus, reporting up to +5.95 accuracy points across six benchmarks.
In: ICML 2024 Workshop on In-Context Learning (2024),https://openreview.net/ forum?id=LjsjHF7nAN23
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VERDICT: Training-Free Step-Wise Verification of Multimodal Reasoning via Disagreement-Aware Consensus
VERDICT verifies each reasoning step of a multimodal LLM by combining scores from three frozen judges through a closed-form consensus, reporting up to +5.95 accuracy points across six benchmarks.